{"id":"https://openalex.org/W4415003108","doi":"https://doi.org/10.1109/lra.2025.3619783","title":"Explicit Memory Through Online 3D Gaussian Splatting Improves Class-Agnostic Video Segmentation","display_name":"Explicit Memory Through Online 3D Gaussian Splatting Improves Class-Agnostic Video Segmentation","publication_year":2025,"publication_date":"2025-10-09","ids":{"openalex":"https://openalex.org/W4415003108","doi":"https://doi.org/10.1109/lra.2025.3619783"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2025.3619783","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lra.2025.3619783","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1109/lra.2025.3619783","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006804543","display_name":"Anthony W. Opipari","orcid":"https://orcid.org/0000-0002-4093-302X"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anthony Opipari","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI, USA","University of Michigan, USA"],"raw_orcid":"https://orcid.org/0000-0002-4093-302X","affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"University of Michigan, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035133232","display_name":"Aravindhan K Krishnan","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aravindhan K Krishnan","raw_affiliation_strings":["Amazon Inc., Kirkland, WA, USA","Amazon Inc., USA"],"raw_orcid":"https://orcid.org/0009-0007-2348-7826","affiliations":[{"raw_affiliation_string":"Amazon Inc., Kirkland, WA, USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Inc., USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053446578","display_name":"Shreekant Gayaka","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shreekant Gayaka","raw_affiliation_strings":["Amazon Inc., Kirkland, WA, USA","Amazon Inc., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Inc., Kirkland, WA, USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Inc., USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Min Sun","orcid":"https://orcid.org/0000-0001-9598-8178"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Min Sun","raw_affiliation_strings":["Amazon Inc., Kirkland, WA, USA","Amazon Inc., USA"],"raw_orcid":"https://orcid.org/0000-0001-9598-8178","affiliations":[{"raw_affiliation_string":"Amazon Inc., Kirkland, WA, USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Inc., USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105792706","display_name":"Cheng-Hao Kuo","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cheng-Hao Kuo","raw_affiliation_strings":["Amazon Inc., Kirkland, WA, USA","Amazon Inc., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Inc., Kirkland, WA, USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Inc., USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053890173","display_name":"Arnie Sen","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arnie Sen","raw_affiliation_strings":["Amazon Inc., Kirkland, WA, USA","Amazon Inc., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Inc., Kirkland, WA, USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Inc., USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071106238","display_name":"Odest Chadwicke Jenkins","orcid":"https://orcid.org/0000-0003-3750-7334"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Odest Chadwicke Jenkins","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI, USA","University of Michigan, USA"],"raw_orcid":"https://orcid.org/0000-0003-3750-7334","affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"University of Michigan, USA","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.28024403,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"10","issue":"12","first_page":"12740","last_page":"12747"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13114","display_name":"Image Processing Techniques and Applications","score":0.9797999858856201,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T13114","display_name":"Image Processing Techniques and Applications","score":0.9797999858856201,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11775","display_name":"COVID-19 diagnosis using AI","score":0.9711999893188477,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9607999920845032,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6518999934196472},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5038999915122986},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.49390000104904175},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4593000113964081},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.44290000200271606},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42899999022483826},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.36070001125335693},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.3555000126361847},{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.3547999858856201}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8289999961853027},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6518999934196472},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6243000030517578},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5038999915122986},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.49390000104904175},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4593000113964081},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.44290000200271606},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42899999022483826},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.36070001125335693},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.3555000126361847},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.3547999858856201},{"id":"https://openalex.org/C37279795","wikidata":"https://www.wikidata.org/wiki/Q2492305","display_name":"Consistency model","level":3,"score":0.3450999855995178},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33329999446868896},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32710000872612},{"id":"https://openalex.org/C12186640","wikidata":"https://www.wikidata.org/wiki/Q6815743","display_name":"Memory model","level":3,"score":0.3255000114440918},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.32269999384880066},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.3172000050544739},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.3147999942302704},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.30379998683929443},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.2962999939918518},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C2781357197","wikidata":"https://www.wikidata.org/wiki/Q5757597","display_name":"High memory","level":2,"score":0.2809999883174896},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.2775999903678894},{"id":"https://openalex.org/C125308379","wikidata":"https://www.wikidata.org/wiki/Q363057","display_name":"Market segmentation","level":2,"score":0.258899986743927},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.25450000166893005}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lra.2025.3619783","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lra.2025.3619783","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2510.23521","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.23521","pdf_url":"https://arxiv.org/pdf/2510.23521","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1109/lra.2025.3619783","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lra.2025.3619783","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Remembering":[0],"where":[1],"object":[2],"segments":[3,91],"were":[4],"predicted":[5,89],"in":[6,39,158],"the":[7,13,40,67,94,117,134],"past":[8],"is":[9],"useful":[10],"for":[11],"improving":[12],"accuracy":[14],"and":[15,64,73,113,138,145,161],"consistency":[16],"of":[17,42,56,96,106],"class-agnostic":[18],"video":[19,23],"segmentation":[20,24,57],"algorithms.":[21],"Existing":[22],"algorithms":[25],"typically":[26],"use":[27,36,116,153,167],"either":[28],"no":[29,168],"object-level":[30,90],"memory":[31,63,120,169],"(e.g.":[32,47],"FastSAM)":[33],"or":[34,170],"they":[35],"implicit":[37,172],"memories":[38,156],"form":[41],"recurrent":[43],"neural":[44,173],"network":[45,174],"features":[46],"SAM2).":[48],"In":[49],"this":[50,101],"paper,":[51],"we":[52,78],"augment":[53],"both":[54,143],"types":[55],"models":[58,69,151],"using":[59],"an":[60,80],"explicit":[61,118,154],"3D":[62,82,155],"show":[65,149],"that":[66,115,150],"resulting":[68],"have":[70],"more":[71,159],"accurate":[72,160],"consistent":[74,162],"predictions.":[75,127],"For":[76],"this,":[77],"develop":[79],"online":[81],"Gaussian":[83],"Splatting":[84],"(3DGS)":[85],"technique":[86],"to":[87,121,132],"store":[88],"generated":[92],"throughout":[93],"duration":[95],"a":[97,104],"video.":[98],"Based":[99],"on":[100],"3DGS":[102,119],"representation,":[103],"set":[105],"fusion":[107],"techniques":[108],"are":[109,130],"developed,":[110],"named":[111],"FastSAM-Splat":[112],"SAM2-Splat,":[114],"improve":[122],"their":[123],"respective":[124],"foundation":[125],"models'":[126],"Ablation":[128],"experiments":[129,148],"used":[131],"validate":[133],"proposed":[135],"techniques'":[136],"design":[137],"hyperparameter":[139],"settings.":[140],"Results":[141],"from":[142],"real-world":[144],"simulated":[146],"benchmarking":[147],"which":[152,166],"result":[157],"predictions":[163],"than":[164],"those":[165],"only":[171],"memories.":[175]},"counts_by_year":[],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-10-10T00:00:00"}